A cost-sensitive attention temporal convolutional network based on adaptive top-k differential evolution for imbalanced time-series classification

Imbalanced time-series classification (ITSC) is ubiquitous in many real-world applications. In this study, a novel cost-sensitive deep learning framework, namely ACS-ATCN, is proposed for ITSC. With the framework of ACS-ATCN, first, weighted class costs are optimized jointly with the hyperparameters of an attention temporal convolutional network (ATCN). Second, an improved evolutionary algorithm, termed adaptive top -k differential evolution (ATDE), is presented for optimizing class costs as well as the network's hyperparameter. Experiments on five data sets demonstrate that ACS-ATCN achieves a higher average G-mean than other cost-sensitive learning and oversampling algorithms while using much less computational time. Comparison between different deep learning frameworks also confirms its advantages over other existing benchmarking methods in ITSC. Experimental results also reveal that ATDE provides more accurate classification than the vanilla DE algorithm, and saves as high as 41.53% of average computational expense for convergence.